Title :
Detecting low-contrast defect regions on glasses using highly robust model-fitting estimator
Author :
Oh, Chang-Hwan ; Joo, Hyonam ; Rew, Keun-Ho
Author_Institution :
Hoseo Univ., Asan
Abstract :
Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low signal-to-noise ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90´s, a highly robust estimator, known as the model-fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional least-square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability 1-epsiv plus an outlier process with probability epsiv. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.
Keywords :
Gaussian noise; computer vision; glass; image segmentation; liquid crystal displays; parameter estimation; white noise; LCD glasses; Mura; Signal-to-Noise Ratio; blemish area; computer vision; contaminated Gaussian mixture; highly robust model-fitting estimator; image background model; low-contrast defect regions; manufacturing process; regular white Gaussian noise model; Computer vision; Costs; Gaussian noise; Glass manufacturing; Manufacturing processes; Noise robustness; Object detection; Object recognition; Productivity; Signal to noise ratio; Defect on LCD Glass; Low-Contrast Defect; Robust Model-Fitting Estimator;
Conference_Titel :
Control, Automation and Systems, 2007. ICCAS '07. International Conference on
Conference_Location :
Seoul
Print_ISBN :
978-89-950038-6-2
Electronic_ISBN :
978-89-950038-6-2
DOI :
10.1109/ICCAS.2007.4406684